A real-world industrial benchmark and agentic baseline show current LLMs often fail to produce correct, stable, deployable visual workflows from natural language, with only modest resolve-rate gains.
Title resolution pending
3 Pith papers cite this work, alongside 1 external citations. Polarity classification is still indexing.
3
Pith papers citing it
1
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A 3B model with few-shot prompting reaches 79.7% of GPT-5 tool-use performance while a hypernetwork adaptation adds zero measurable benefit across four benchmarks.
Proposes autopoietic architectures for self-constructing software as a fundamental shift in the SDLC, leveraging foundation models for autonomous evolution and maintenance.
citing papers explorer
-
Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language
A real-world industrial benchmark and agentic baseline show current LLMs often fail to produce correct, stable, deployable visual workflows from natural language, with only modest resolve-rate gains.
-
Meta-Tool: Efficient Few-Shot Tool Adaptation for Small Language Models
A 3B model with few-shot prompting reaches 79.7% of GPT-5 tool-use performance while a hypernetwork adaptation adds zero measurable benefit across four benchmarks.
-
Towards Enabling An Artificial Self-Construction Software Life-cycle via Autopoietic Architectures
Proposes autopoietic architectures for self-constructing software as a fundamental shift in the SDLC, leveraging foundation models for autonomous evolution and maintenance.